FIELDimageR:
Performing image analysis in plant breeding programs

Introduction

Image phenotyping platforms

Image phenotyping platforms are a fast and non-invasive tool for phenotyping plant under lab and field conditions. The most common are sensors for imaging. The reflected light captured in these images can be used to draw inference about many traits, including:

  • Geometric traits (i.e. plant height, leaf area index, lodging, crop canopy cover)
  • Canopy spectral texture (spectral features)
  • Physiological traits (i.e., chlorophyll, biomass, pigment content, photosynthesis)
  • Abiotic/biotic stress indicators (i.e., stomatal conductance, canopy temperature difference, leaf water potential, senescence index)
  • Nutrients (nitrogen concentration, protein content)
  • Yield

Image segmentation

Image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels or image objects).

Thresholding

Thresholding is the simplest method of image segmentation. This method is based on a clip-level (or a threshold value) to turn a gray-scale image into a binary image (Mask).

FIELDimageR

FIELDimageR is a R package to analyze images from research fields, and allows to:

  • Crop the image
  • Remove the background
  • Build vegetation indices
  • Rotate the image
  • Build the plot shapefile
  • Extract information for each plot

1) Example 01

Counting green seeds in Soybean

Alexandre Abdão(Embrapa Maize & Sorghum)

  • 4 pictures: soybean samples with different green seeds percentage

  • Number of green seeds (0, 1, 6, and 11)

  • Donwload: soybean.zip

Required packages

  • Uploading one image as example and decreasing the resolution

2) Example 02

Remote sensing (Potato Breeding)

Jeffrey Endelman and Filipe Matias (UW-Madison)

  • Evaluating each trial per time:

  • Estimation of plant height using a high throughput phenotyping platform. (Donwload: dsm.tif)

  • Heritability

Reference

Matias, F.I. (2019). FIELDimageR Pipeline (tutorial). https://github.com/filipematias23/FIELDimageR

Matias, F.I.; Caraza-Harter, M.; Endelman, J.B. (2020). FIELDimageR: A R Package to Analyze Orthomosaic Images from Agricultural Field Trials. The Plant Phenome Journal. DOI:10.1002/ppj2.20005

Filipe Matias
Department of Horticulture
University of Wisconsin-Madison

2020-10-17